Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to the physical characteristics and features of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and the presence of ending sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.89
     particip
    -0.79
     volunteering
    -0.78
     imperson
    -0.77
     acad
    -0.76
     anarchy
    -0.76
     concess
    -0.74
     divest
    -0.74
     professions
    -0.73
     taboo
    -0.73
    POSITIVE LOGITS
     Compared
    1.50
     Designed
    1.36
     Specifications
    1.36
     Its
    1.35
     Unfortunately
    1.33
     Unlike
    1.33
     Featuring
    1.31
     However
    1.29
     Additionally
    1.28
     Otherwise
    1.25
    Act Density 0.246%

    No Known Activations